NeurIPS 2026 Papers

Low-Rank Adaptation (LoRA) fusion enables the composition of subject and style representations for controllable generation without retraining. However, existing approaches primarily operate through weight-level merging, without explicitly modeling how independently trained LoRAs interact in the shared parameter space. We adopt a geometric perspective on LoRA fusion, interpreting content and style LoRAs as occupying overlapping, non-orthogonal low-rank subspaces, where such overlap can lead to conflicting parameter updates that affect generation quality. This observation motivates us to reformulate LoRA fusion not merely as parameter combination, but as a problem of controlling how updates from overlapping subspaces are combined. Based on this insight, we propose Null Space Projection LoRA (NP-LoRA), a training-free framework that employs projection as a fusion operator to explicitly modulate cross-LoRA interactions. Specifically, NP-LoRA uses principal directions of the style LoRA to define a projection subspace and projects the content LoRA onto the complementary subspace (i.e., the null space of the style LoRA), suppressing interference along dominant style directions while preserving complementary information. To avoid the overly aggressive suppression of hard projection, we further formulate soft projection as a regularized optimization problem that balances content preservation against style-subspace suppression. This objective admits a closed-form solution, yielding a projection operator controlled by a single parameter that continuously interpolates between linear merging and hard projection. Extensive experiments across multiple pretrained LoRA pairs show that NP-LoRA achieves more balanced content-style composition compared to strong baselines, without requiring retraining.

Discovering explanatory subgraphs is essential for interpreting Graph Neural Networks (GNNs). Many existing and popular explainers optimize by maximizing mutual information (MMI) between selected subgraphs and predicted labels; however, the resulting optimization landscape is often non-smooth and poorly conditioned, leading to suboptimal local optima. To address this issue, we develop a norm-theoretic framework for subgraph analysis. We show that subgraphs containing model-utilized features tend to induce graph embeddings with larger $\ell_2$ norms, as they align more strongly with the supportive subspace shaped by the GNN’s weight matrices, a phenomenon consistently observed across multiple datasets. Based on this insight, we propose NORMA, a parameterized explainer that uses subgraph-embedding $\ell_2$ norms as a stable optimization signal to guide subgraph selection. Experiments on fsix benchmark datasets demonstrate that NORMA effectively alleviates the optimization difficulties of MMI-based methods and achieves superior explanation quality.

Learning effective representations from battery operational history is essential for predictive health management and control-oriented applications. Existing approaches rely on response-dependent engineered features or short early-life windows, limiting generalisability and precluding use in prospective settings where future responses are unavailable. We propose $\texttt{NOCE-Net}$, a deep nested sequence model that learns control-enabling representations directly from raw cyclic operational data. Our data pipeline, $\texttt{re-BatteryData}$, standardises heterogeneous aging datasets into semantically equivalent Full Equivalent Cycles (FECs) defined by absolute charge throughput, enabling end-to-end learning across diverse operational regimes. $\texttt{NOCE-Net}$ combines multi-patch transformer encoders for intra-cycle dynamics with a GRU backbone for inter-cycle state evolution, operating on approximately $700$ batteries across ten public datasets spanning over $300$ operational profiles. In zero-shot evaluation on unseen battery chemistries and usage patterns, $\texttt{NOCE-Net}$ achieves $13.7$% MAPE in voltage response prediction, outperforming strong long-sequence baselines by over $43$% while using $40 \times$ fewer parameters. Shape and component diagnostics of the learned hidden states reveal that the GRU's principal direction of evolution achieves Spearman $|\rho| \geq 0.95$ with the capacity fade trajectory on average across all datasets with monotone degradation profiles, including zero-shot test batteries, providing evidence that the representations encode degradation dynamics transferable to downstream tasks beyond battery response modelling.

Survival models are often trained at target clinical sites where outcomes are limited and censored, while patient-level data from external cohorts may be unavailable because of institutional data-sharing constraints. In many applications, the transferable knowledge is not a dataset, a calibrated survival curve, or estimated regression coefficients, but a probability-free prognostic artifact such as a clinician-defined scorecard, guideline-based staging rule, registry-derived risk index, or coarse clinical risk group. These weak teachers may encode human expertise or evidence from prior cohorts, yet they often have only ordinal meaning and need not share a numerical scale with the target model. We propose NNCoxKL, a transfer-learning framework that trains a deep Cox model on target time-to-event data while distilling such human- or model-derived prognostic signals through Cox risk sets. For each event risk set, NNCoxKL converts both the external signal and the neural Cox risk score into Plackett--Luce distributions and regularizes the Cox partial likelihood through a temperature-scaled KL alignment term. This transforms clinical knowledge into a censoring-aware ranking prior over who is most likely to fail next, rather than treating the external score as a covariate or requiring it to represent calibrated survival probabilities. The external signal enters only through this risk-set regularizer, allowing the model to learn nonlinear target-cohort effects while borrowing relative-risk information from external clinical knowledge. Experiments on independent clinical transfer tasks and controlled survival benchmarks show that NNCoxKL improves discrimination and calibration-sensitive prediction over internal-only deep Cox models and common score-transfer baselines.

Variable fonts enable continuous variation of glyph geometry along semantic design axes such as weight, width, slant, and optical size. However, constructing a variable font from a static font remains a labor-intensive process requiring expert typographic design and manual specification of glyph variation data. We introduce NIV (Neural Axis Variations), a method that automatically converts a static font into a fully functional variable font. Given glyph outlines and a set of desired design axes, NIV predicts per-point displacements. The model operates directly on vector glyph geometry and employs a novel Property Embedding mechanism that captures interactions between multiple axes, enabling consistent multi-axis variation within a unified framework. We train NIV on a newly constructed dataset derived from variable Google Fonts, comprising over one million variation tuples. The resulting model generalizes across unseen code points, unseen font styles, high-complexity CJK glyphs, and even out-of-distribution handwriting inputs. The generated outputs are standard variable font files supporting continuous interpolation via existing rendering engines. To facilitate research, we release the dataset, the complete training and inference implementation, and trained models. Beyond typography, our approach demonstrates how structured geometric objects with continuous parametric variation can be synthesized using neural deformations.

Recent advances in agent-based methods have demonstrated strong promise for issue localization, a critical prerequisite for software issue resolution. However, most existing agent-based methods rely on a single agent with a growing context, where long-context accumulation compresses the effective reasoning space. Meanwhile, the flat exploration structure hinders the balance between file-level breadth and function-level depth. To address these limitations, we propose NINJA, a hierarchical Navigator-INspector Joint Architecture for context-efficient issue localization. NINJA decomposes repository exploration into global navigation and local inspection: the navigator maintains the global search state, performs file-level search, and dispatches selected entry files, while inspectors independently conduct function-level exploration around the assigned files in separate contexts. Through multi-round interactions, inspectors return suspicious locations as feedback, and the navigator updates the global state to decide whether to continue exploration or finalize localization. This hierarchical design balances file-level breadth with function-level depth, while independent inspector contexts prevent local exploration traces from accumulating in a single growing context. To further strengthen both global coordination and local exploration, we introduce a two-stage agentic fine-tuning strategy. Extensive experiments across multiple benchmarks and LLM backbones show that NINJA consistently outperforms competitive baselines. Notably, after fine-tuning, Qwen3-Coder-30B-A3B-Instruct surpasses the strong closed-source Claude-Haiku-4.5 model. Our code is available at https://anonymous.4open.science/r/NINJA-67FB/.

Implicit neural video representations offer compact, continuous alternatives to conventional codecs, but higher reconstruction fidelity typically requires more computation per decoded frame. We introduce NIKA, which shifts video-specific capacity from the decoder into a structured latent state, allowing reconstruction quality to scale with latent expressivity while keeping active decoding lightweight. NIKA constructs this state from complementary spatial, spectral, and temporal bases, then decodes it with lightweight ConvNeXt-style convolutional upsampling. On UVG, a 2.91M-parameter NIKA model achieves 33.33 dB PSNR at 462 decoding FPS with 4.5G MACs on an RTX A5000, outperforming comparable single-resolution NeRV-family baselines while using 39--51$\times$ fewer MACs. Ablations show that diversifying latent components improves reconstruction more reliably than reallocating capacity within a single component, and qualitative analysis reveals specialization among components. Together, these results identify structured latent diversity as a practical alternative to scaling decoder complexity for high-fidelity, efficient neural video representation.

Neural Graph Databases (NGDBs) support complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-only embeddings. We present NGDB-Zoo, a unified framework that resolves these bottlenecks by synergizing operator-level training with semantic augmentation. By decoupling logical operators from query topologies, NGDB-Zoo transforms training loops into dynamically scheduled data-flow executions, enabling multi-stream parallelism and achieving a $1.8\times$-$6.8\times$ average throughput compared to baselines. Furthermore, we formalize a decoupled architecture to integrate semantic priors from pre-trained text embeddings without triggering I/O stalls or memory overflows. Experiments on six benchmarks, including $\textit{ogbl-wikikg2}$ and $\textit{ATLAS-Wiki}$, show that NGDB-Zoo scales dense query-embedding training to million-entity graphs while maintaining competitive filtered MRR.

Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model (LLM) agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore steganographic CoT---where models hide secret reasoning within innocuous text---to inform risk assessment and deployment policies. Steganographic reasoning requires two skills in a single forward pass: computing an intermediate result, and embedding it into a coherent cover that answers an unrelated question. Drawing on our taxonomy of steganographic and non-steganographic CoT types, we systematically evaluate the limits of prompt-elicited steganographic CoT capability across 34 models, ranging from past generations to the current frontier. We measure monitor evasion, refusal rates, encoding fidelity, and hidden task accuracy across five datasets, comparing against plain reasoning, direct answer, and filler-token baselines. The two experiments isolate the two sub-skills: a reasoning tasks sweep tests joint reason-and-embed, while a counting task hands the model a known numerical sequence and tests embedding alone---a necessary precondition for stego reasoning. Current frontier models cannot sustain joint reason-and-embed: a paired McNemar comparison shows the steganographic channel is dominated by an filler-token baseline on every (model, family) cell. The encoding-only floor, by contrast, is cleared---Claude Opus~4.5 reaches 92\% per-number partial accuracy (54\% exact-match) on 4-digit sequences and saturates at 100\% exact-match on length-8 single-digit sequences---establishing that the binding constraint on stego CoT is the joint reasoning-plus-encoding load, not raw channel capacity. Separately, GPT-5.2 issues an explicit refusal to the steganographic instruction yet still produces partial valid encoding in 6 of 644 trials. Our findings underscore the need for continuous evaluation of steganographic risk and provide a methodology to preemptively detect and evaluate hidden reasoning that might empower misaligned scheming and deceptive behavior.

Transformer-based autoregressive models offer an efficient alternative to diffusion- and flow-matching-based approaches for generating 3D molecules. One challenge remains: standard transformer architectures require a sequential ordering of tokens, which is not inherently defined for the atoms in a molecule. Prior works have addressed this by using canonical atom orderings. However, these approaches are not permutation invariant w.r.t. atoms and bias next-token prediction towards ordering conventions. We overcome this limitation by introducing a novel neighborhood-guided training strategy. Our model, NEAT (Neighborhood-Guided, Efficient, Autoregressive Set Transformer) treats molecular graphs as sets of atoms and learns an order-agnostic distribution over admissible tokens at the graph boundary, thereby ensuring atom-level permutation invariance. NEAT achieves state-of-the-art generation quality on the QM9 and GEOM-Drugs datasets while offering a significant speed advantage over existing baselines.

Task-oriented dexterous grasp generation aims to produce dexterous grasp poses that are both physically plausible and functionally suitable for specified manipulation tasks. Existing diffusion-based methods often address these two requirements in a decoupled manner: they first train a grasp diffusion model for task alignment and then rely on post-generation refinement to improve physical plausibility. However, this after-the-fact correction strategy applies physical plausibility guidance only once the grasp has already been generated, leaving the generation trajectory itself unguided by physical constraints and potentially leading to suboptimal grasps. To address this problem, we propose a novel framework that directly injects physical plausibility guidance into the denoising process of a task-aligned grasp diffusion model in a practical and effective manner, even when physical plausibility constraints are non-differentiable. This allows physical plausibility to shape grasp generation throughout denoising while preserving task alignment. Extensive experiments demonstrate the efficacy of our framework.

Augmenting model-free reinforcement learning (RL) with representations learned through observation dynamics prediction (observation-predictive RL) can improve sample efficiency and performance, with minor modifications and limited additional computation. However, this approach still struggles in challenging tasks with low-dimensional observations. In this paper, we identify a key factor behind this problem: unbalanced reconstruction losses across observation dimensions, where dimensions with larger value ranges dominate the loss. This encourages the agent to neglect dimensions with relatively small ranges, leading to degraded performance. To address this issue, we propose a novel normalization method tailored to online RL, which normalizes low-dimensional observations and balances the resulting losses and gradients. Beyond balancing reconstruction losses, observation normalization enables dynamics prediction to be performed in a normalized observation space, thereby providing a unified treatment of low- and high-dimensional inputs (e.g., physical states and images). Building on this idea, we further introduce Normalized Observation Space Dynamics-Augmented Q-learning (NASDAQ), a framework for observation-predictive RL applicable across diverse domains. NASDAQ learns state-action representations by coupling value learning with two auxiliary tasks: short-term value prediction and next *normalized* observation prediction. Extensive experiments demonstrate that NASDAQ achieves competitive or superior performance compared with state-of-the-art model-based and self-predictive RL methods, while requiring significantly less training wall-time.

Interactive narrative is becoming a practical frontier for language-model agents, spanning game NPCs, collaborative story production, emotionally responsive companions, and story-grounded interface generation. Yet most current evaluations still rely on static prompts, isolated story outputs, or post-hoc ratings, leaving open whether frontier models can sustain coherent, adaptive, emotionally grounded interaction over time. We introduce NARRA-Gym, an executable evaluation environment that turns a sparse emotional seed into a complete interactive story episode and records the full agent loop: story construction, memory updates, planning, pacing control, and optional artifact generation. The benchmark jointly tests five coupled capabilities---creative story generation, long-context state tracking, character simulation, empathic personalization, and interactive artifact generation---through a fixed LLM-as-judge sweep and a human preference study with user-provided experiences. Across nine generator models and eight benchmark personas, Claude Sonnet 4.6 is the strongest and most robust performer, while Claude Opus 4.6 forms a high-variance second tier and several middle-tier models show different tradeoffs between story quality and user experience. Human rankings recover the same top tier but shift the middle of the ordering, indicating that automated judges are useful for broad screening while human preference remains important for style, tone, and emotional resonance. Finally, failure analysis shows that the key remaining bottleneck is not surface fluency but resistance-sensitive personalization: models can write polished scenes while losing track of what the user is resisting or emotionally unable to accept.

Sparse-view novel view synthesis is a central problem in 3D content creation, but diffusion-based approaches remain limited by iterative denoising, making multi-view generation expensive at inference time. We introduce NAMVIS, a diffusion-free framework that reformulates multi-view image synthesis as geometry-conditioned next-scale autoregression. Instead of generating target views through repeated denoising, NAMVIS predicts discrete visual tokens through a small number of coarse-to-fine scale steps, while sampling all tokens within each scale and across target views in parallel. To anchor this generation process to explicit camera geometry, we propose Multi-scale Projective Pose Encoding, which injects source and target camera transformations into both target-view self-attention and source-to-target cross-attention at every resolution. NAMVIS further combines global conditioning with dense geometry-aware cross-attention, enabling the model to preserve source-view appearance while maintaining target-view consistency. Across Objaverse, GSO, and OmniObject3D, NAMVIS outperforms diffusion-based baselines in PSNR, SSIM, and LPIPS, while running over 3× faster than the evaluated diffusion baselines under the same evaluation setting. These results suggest that geometry-conditioned next-scale autoregression is a promising and efficient alternative to diffusion for sparse-view multi-view synthesis.

We introduce NAGO, a noise-aware generative operator for efficient sampling from invariant measures of stochastic partial differential equations (SPDEs) in function space. Our central idea is to treat the noise measure as a design variable rather than a fixed default. While existing generative approaches mainly shape the sampling process through interpolation schedules or guidance heuristics, NAGO directly controls the marginal velocity field in functional flow matching by choosing a noise measure with suitable regularity. We establish conditions under which the resulting noise-induced flows are well defined in infinite-dimensional settings, and show how noise regularity affects the spectral geometry and stiffness of the marginal velocity field. This analysis leads to a principled design rule: match the regularity of the noise measure to that of the target invariant measure. The resulting method enables stable training and fast sampling without relying on downstream correction mechanisms. Experiments on three representative SPDEs with multiscale invariant measures show that NAGO consistently improves the accuracy--efficiency trade-off over standard flow matching baselines, while achieving up to two orders of magnitude speedup compared with classical numerical solvers.

Catastrophic forgetting is a central obstacle in single-stage fine-tuning of large language models (LLMs) on a new task, especially when the original pretraining data are unavailable. Synthetic data offers a practical mitigation path, but candidate pools are often noisy and redundant, making effective selection essential. Existing methods often rely on indirect proxy signals whose alignment with actual training benefit can be limited, while utility--diversity selection over large candidate pools remains computationally demanding. To address these challenges, we propose $\textbf{NA}$vigator-guided $\textbf{D}$ata $\textbf{S}$election ($\textbf{NADS}$), a fine-tuning framework for LLMs. NADS first follows the target fine-tuning recipe without preservation regularization to obtain a navigator model, whose deviation from the pretrained model exposes recipe-induced capability drift. It then uses the predictive divergence between the navigator and the pretrained model to score forgetting-aware utility for each synthetic candidate, and constructs a constraint set through an efficient utility--diversity selection strategy. Finally, NADS fine-tunes on the new-task data while distilling pretrained behavior on the selected constraints to preserve general capabilities. Experiments show that NADS delivers a stronger balance between new-task performance and general capability preservation, while reducing utility--diversity selection overhead.

Improving the inference efficiency of autoregressive transformers typically means reducing FLOPs per token, usually through approximations that degrade model quality. We introduce N-vium, a mixture-of-exits transformer that partially parallelizes computation across depth on standard hardware, increasing effective FLOPs per second rather than minimizing compute per token. N-vium attaches prediction heads at multiple depths and defines the next-token distribution as a learned mixture over these exits, with token-adaptive routing. This formulation strictly generalizes the standard transformer, which is recovered exactly when routing assigns zero mass to all intermediate heads. Sampling from the mixture is exact, and complete KV caches are recovered by deferring the upper-layer computation and batching it with later tokens. We pretrain N-vium at scales up to 1.5B parameters. Our largest model reaches 57.9% wall-clock speedup over a parameter- and data-matched standard transformer at no perplexity cost.

Athletic performance represents the pinnacle of human motor intelligence, demanding rapid choices, precise control, agility, and coordinated physical execution. Replicating this seamless combination of capabilities remains elusive in current artificial intelligence and robotic systems. Concurrently, understanding the biological mastery of these movements is hindered because complex muscle coordination is rarely measured in vivo due to the limitations of physical equipment. To bridge this fundamental gap in understanding, $\textit{MyoChallenge}$ at NeurIPS 2025 established a pioneering benchmark for motor control intelligence in sports, leveraging high-fidelity musculoskeletal models within physics simulation combined with machine learning-driven algorithms. The competition introduces two distinct tracks emphasizing either upper or lower limbs control: a table tennis rally task utilizing a biomechanic upper limb composed of an arm with a hand (MyoArm) and a trunk (MyoTorso); and a soccer penalty kick using a biomechanic model of legs (MyoLeg) and a trunk (MyoTorso). Marking the fourth iteration of the MyoChallenge series, this event attracted almost 70 teams and over 560 submissions globally, uniting a diverse community ranging from physicians and neuroscientists to machine learning experts. The competition facilitated the development of several state-of-the-art control algorithms for a musculoskeletal system capable of sports agility, leveraging techniques such as physics-based motion planners, on-policy behaviour cloning, hierarchical planning, and muscle synergies that significantly surpassed our provided baseline performance. By integrating standardized tasks and physiologically realistic models into the open-source framework of MyoSuite, MyoChallenge'25 serves as a reproducible and reusable testbed to accelerate interdisciplinary research across machine learning, biomechanics, sports science, and neuroscience. Project page: https://www.myosuite.org//myochallenge/myochallenge-2025

Recent diffusion-based video generation models have enabled high-quality video customization through both tuning-based pipelines, which fine-tune a video diffusion model, and reference-based pipelines such as image-to-video generation. However, these capabilities raise serious concerns about facial privacy and security. Existing anti-diffusion protections focus on the image domain or on reference-based I2V pipelines, leaving the tuning-based video customization unexplored. Protecting videos in this setting raises three challenges: image-level perturbations are erased by temporal operations, a perturbation tied to one clip fails to generalize across videos and lengths, and inconsistent temporal noise is easily removed by temporal attack. To address these challenges, we propose Temporally Consistent Universal Adversarial Perturbations (TC-UAP), the first protection method against both reference- and tuning-based video customization. TC-UAP learns a multi-frame universal adversarial perturbation over a set of videos of the same identity, so that a single perturbation can transfer to unseen videos and arbitrary clip lengths of that identity. Besides, we further enforce consistency through intrinsic temporal modeling and an extrinsic surrogate temporal-attack loss, ensuring robustness against temporal attacks. Extensive quantitative and qualitative experiments show that TC-UAP degrades identity preservation more than existing baselines under both tuning-based and reference-based video customization, and remains robust under three unseen temporal attacks.